Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.8418. Min Act: -0.1700
Data Index: 965428 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3755587 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.4043. Min Act: -0.1700
Data Index: 6176773 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.4043. Min Act: -0.1700
Data Index: 3826376 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.3418. Min Act: -0.1700
Data Index: 1902457 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.3105. Min Act: -0.1700
Data Index: 6190315 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.2480. Min Act: -0.1700
Data Index: 7307519 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.2168. Min Act: -0.1700
Data Index: 7766596 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.2168. Min Act: -0.1700
Data Index: 6111938 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1855. Min Act: -0.1700
Data Index: 8081664 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1855. Min Act: -0.1700
Data Index: 2062438 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1855. Min Act: -0.1700
Data Index: 7288860 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1543. Min Act: -0.1700
Data Index: 4706816 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1230. Min Act: -0.1700
Data Index: 6190311 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1230. Min Act: -0.1700
Data Index: 5167008 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.0605. Min Act: -0.1700
Data Index: 4141393 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.0605. Min Act: -0.1700
Data Index: 4625281 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8136580 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8508884 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8418. Min Range: -5.8418
Max Act: 5.1230. Min Act: -0.1700
Data Index: 4100014 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19